Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    comments or annotations in the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hardware register definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -0.49
     Italij
    -0.48
    ":[{
    -0.47
     󰀄
    -0.46
     Penelitian
    -0.45
    csolódó
    -0.45
     ब्रेकडाउन
    -0.44
     håll
    -0.44
     Pristupljeno
    -0.44
     parís
    -0.44
    POSITIVE LOGITS
    ola
    0.54
     FRA
    0.52
     mAdapter
    0.51
    auto
    0.50
     */
    0.50
    aktu
    0.50
    ſt
    0.49
     Kab
    0.49
     Fru
    0.48
     Nim
    0.48
    Act Density 0.010%

    No Known Activations